Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1069 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.6495. Min Act: -0.0001

Data Index: 222278 (C4 (Web Text))

Max Activating Token Index: 1013

Text #1

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.6806. Min Act: -0.0001

Data Index: 940173 (C4 (Web Text))

Max Activating Token Index: 750

Text #2

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.6140. Min Act: -0.0001

Data Index: 478007 (C4 (Web Text))

Max Activating Token Index: 243

Text #3

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.6412. Min Act: -0.0001

Data Index: 109785 (C4 (Web Text))

Max Activating Token Index: 930

Text #4

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.6636. Min Act: -0.0001

Data Index: 783930 (C4 (Web Text))

Max Activating Token Index: 198

Text #5

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5628. Min Act: -0.0001

Data Index: 706261 (C4 (Web Text))

Max Activating Token Index: 582

Text #6

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.6165. Min Act: -0.0001

Data Index: 612247 (C4 (Web Text))

Max Activating Token Index: 736

Text #7

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5505. Min Act: -0.0001

Data Index: 1070376 (C4 (Web Text))

Max Activating Token Index: 620

Text #8

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.6422. Min Act: -0.0001

Data Index: 226712 (C4 (Web Text))

Max Activating Token Index: 570

Text #9

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5925. Min Act: -0.0001

Data Index: 350018 (C4 (Web Text))

Max Activating Token Index: 197

Text #10

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5319. Min Act: -0.0001

Data Index: 893928 (C4 (Web Text))

Max Activating Token Index: 600

Text #11

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5746. Min Act: -0.0001

Data Index: 1056113 (C4 (Web Text))

Max Activating Token Index: 1017

Text #12

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5960. Min Act: -0.0001

Data Index: 708725 (C4 (Web Text))

Max Activating Token Index: 76

Text #13

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5724. Min Act: -0.0001

Data Index: 590048 (C4 (Web Text))

Max Activating Token Index: 1018

Text #14

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5488. Min Act: -0.0001

Data Index: 246457 (C4 (Web Text))

Max Activating Token Index: 701

Text #15

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5482. Min Act: -0.0001

Data Index: 897211 (C4 (Web Text))

Max Activating Token Index: 162

Text #16

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.6295. Min Act: -0.0001

Data Index: 212459 (C4 (Web Text))

Max Activating Token Index: 857

Text #17

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.4976. Min Act: -0.0001

Data Index: 179761 (C4 (Web Text))

Max Activating Token Index: 35

Text #18

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.4998. Min Act: -0.0001

Data Index: 709604 (C4 (Web Text))

Max Activating Token Index: 586

Text #19

Max Range: 0.6806. Min Range: -0.6806

Max Act: 0.5283. Min Act: -0.0001

Data Index: 1011195 (C4 (Web Text))

Max Activating Token Index: 786